菜单
Build Docker images and launch a local preview environment with docker-compose. Use to test the full stack locally before merging.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/xvirobotics/metaskill --skill deploy-preview命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | deploy-preview |
| description | Build Docker images and launch a local preview environment with docker-compose. Use to test the full stack locally before merging. |
| user-invocable | true |
| disable-model-invocation | true |
| context | fork |
| allowed-tools | Bash, Read, Grep |
You are a deployment preview agent. Your job is to build and launch a local preview environment using Docker, then verify it is healthy.
Current branch: !git branch --show-current
Git status: !git status --short
docker --version && docker compose version
If Docker is not available, report that Docker must be installed and stop.
docker compose -f docker-compose.yml down --remove-orphans 2>/dev/null || true
Build the application image using the multi-stage Dockerfile:
docker compose -f docker-compose.yml build --no-cache
If the build fails, report the full error output. Common issues: missing files in build context (check .dockerignore), npm install failures, TypeScript compilation errors.
docker compose -f docker-compose.yml up -d
Wait for services to be healthy:
echo "Waiting for services to start..."
sleep 5
docker compose -f docker-compose.yml ps
docker compose -f docker-compose.yml exec -T app npx prisma migrate deploy
If migrations fail, report the error. Common issues: database not ready yet (may need longer wait), migration conflicts.
Verify the application is responding:
curl -sf http://localhost:3000/api/health || echo "HEALTH CHECK FAILED"
If the health check fails, inspect the logs:
docker compose -f docker-compose.yml logs --tail=50 app
## Preview Deployment Results
**Branch:** [branch name]
**Status:** RUNNING / FAILED at [step]
### Services
| Service | Status | Port |
|---------|--------|------|
| app | running/stopped | 3000 |
| db | running/stopped | 5432 |
| client | running/stopped | 5173 |
### Access URLs
- API: http://localhost:3000/api
- Frontend: http://localhost:5173
- Health: http://localhost:3000/api/health
### Cleanup
To stop the preview environment:
docker compose -f docker-compose.yml down
Load the latest model checkpoint, run evaluation on the test set, and generate a metrics report with confusion matrix. Use this after training to assess model performance or to re-evaluate a specific checkpoint.
Generate a comprehensive summary report of the latest experiment including metrics, plots, and comparison with baseline. Use this after training and evaluation to create a shareable experiment summary.
Run the full data science pipeline: validate raw data, preprocess, engineer features, train model, and evaluate. Use this when you want to execute the end-to-end ML pipeline or re-run it after data or code changes.